HMRFS–TP: long-term daily gap-free snow cover products over the Tibetan Plateau from 2002 to 2021 based on hidden Markov random field model

Abstract

Abstract. Snow cover plays an essential role in climate change and the hydrological cycle of the Tibetan Plateau. The widely used Moderate Resolution Imaging Spectroradiometer (MODIS) snow products have two major issues: massive data gaps due to frequent clouds and relatively low estimate accuracy of snow cover due to complex terrain in this region. Here we generate long-term daily gap-free snow cover products over the Tibetan Plateau at 500 m resolution by applying a hidden Markov random field (HMRF) technique to the original MODIS snow products over the past two decades. The data gaps of the original MODIS snow products were fully filled by optimally integrating spectral, spatiotemporal, and environmental information within HMRF framework. The snow cover estimate accuracy was greatly increased by incorporating the spatiotemporal variations of solar radiation due to surface topography and sun elevation angle as the environmental contextual information in HMRF-based snow cover estimation. We evaluated our snow products, and the accuracy is 98.29 % in comparison with in situ observations, and 91.36 % in comparison with high-resolution snow maps derived from Landsat images. Our evaluation also suggests that the incorporation of spatiotemporal solar radiation as the environmental contextual information in HMRF modeling, instead of the simple use of surface elevation as the environmental contextual information, results in the accuracy of the snow products increases by 2.71 % and the omission error decreases by 3.59 %. The accuracy of our snow products is especially improved during snow transitional period, and over complex terrains with high elevation and sunny slopes. The new products can provide long-term and spatiotemporally continuous information of snow cover distribution, which is critical for understanding the processes of snow accumulation and melting, analyzing its impact on climate change, and facilitating water resource management in Tibetan Plateau. This dataset can be freely accessed from the National Tibetan Plateau Data Center at https://doi.org/10.11888/Cryos.tpdc.272204 (Huang and Xu, 2022).

Using music and music‐based analysis to model and to classify terrain in geomorphology

“…Further, supervised learning was used to establish the landform recognition framework as it has long been recognized as an effective paradigm in landform recognition and classification (Drăguţ & Blaschke, 2006; Prima et al, 2006). Five popular supervised machine learning algorithms, namely, light gradient boosting machine (LightGBM) (Zhang et al, 2019), random forest (RF) (Huang et al, 2022), extreme gradient boosting algorithm (XGBoost) (Chen & Guestrin, 2016), gradient‐boosted decision tree (GBDT) (Shang et al, 2023) and support vector machine (SVM), were utilized. Due to the lack of room, we did not provide detailed descriptions of these algorithms.…”

Spatiotemporal Variations in Snow Cover on the Tibetan Plateau from 2003 to 2020

“…Utilizing the Hidden Markov Random Field (HMRF) modeling technique, it generates daily snow cover data with a spatial resolution of 500 m without any gaps spanning from 2002 to 2022 across the Tibetan Plateau. The HMRF framework effectively integrates spectral, temporal, and environmental information to fill data gaps resulting from frequent cloud cover while enhancing the accuracy of the original MODIS snow products [35]. In this study, the dataset primarily serves to capture changes in snow cover duration from 2003 to 2020.…”

MODIS daily cloud-gap-filled fractional snow cover dataset of the Asian Water Tower region (2000–2022)

“…As (Ault et al, 2006;Ke et al, 2016;Zhang et al, 2019;Wang et al, 2022). Therefore, this study refers to previous studies to binarize the snow depth data with a threshold of 3 cm in the AWT region (Yang et al, 2015;Zhang et al, 2019;Huang et al, 2022a, b); i.e., snow depths less than 3 cm are classified as no snow and those greater than 3 cm are classified as snow. To further illustrate the accuracy of snow identification, this study excluded stations with snow depths greater than 1 cm but snow cover days less than 20 (Zhang et al, 2020;Hao et al, 2021).…”

“…Terra and Aqua MODIS provides two daily daytime observations, but the MODIS annual average cloud cover in the Asian Water Tower region is approximately 50 % (Wang et al, 2019;Huang et al, 2022a). Snow cover observations can be obscured by clouds, resulting in many data gaps in daily snow cover products, which greatly limits the application of daily snow cover products.…”

“…Currently, there are various snow cover datasets for the Asian Water Tower region, such as the Interactive Multisensor Snow and Ice Mapping System (IMS) (Mazari et al, 2013), MODIS/Terra Snow Cover Daily L3 Global 500 m SIN Grid product (MOD10A1/MOD10A1F) (Hall and Riggs, 2016), MODIS Snow-Covered Area and Grain size product (MODSCAG) (Painter et al, 2009), Japan Aerospace Exploration Agency (JAXA) long-term snow cover extent dataset (JASMES) (Hori et al, 2017), Northwest Institute of Eco-Environment and Resources (NIEER), Chinese Academy of Sciences AVHRR/MODIS snow cover extent product (NIEER AVHRR/MODIS SCE) (Hao et al, 2021(Hao et al, , 2022, Tibetan Plateau long-term daily gap-free snow cover product based on the Hidden Markov Random Field model (HMRFS-TP) (Huang et al, 2022a), the European Space Agency (ESA) Snow Climate Change Initiative (Snow CCI: MODIS (Nagler et al, 2022) and AVHRR (Naegeli et al, 2022. The IMS, JASMES and NIEER AVHRR SCE products are binary products and have relatively coarse reso-lutions.…”